Description du projet
Cartographie révolutionnaire et automatisée du gamut pour le web, les téléphones portables et l’usage professionnel
Les consommateurs exigent des images et des vidéos de plus en plus réalistes, que ce soit sur leur téléphone portable, leur téléviseur ou le grand écran. La cartographie du gamut est utilisée pour modifier les couleurs d’origine et optimiser l’affichage lorsque les couleurs à reproduire sortent du gamut ou des capacités du système d’affichage. Le projet GAMMAVISION, financé par l’UE, produit une gamme de produits qui illustrent la méthode de cartographie du gamut automatique et fondée sur la vision précédemment développée par l’équipe, qui a affiché des performances supérieures aux algorithmes de pointe en termes de préférences de l’utilisateur. Les résultats comprendront une application web gratuite et des applications mobiles commerciales pour les systèmes iOS et Android, ainsi que des extensions commerciales pour les logiciels professionnels de post-production de films et de photos.
Objectif
The color gamut of a display is the set of colors that it can reproduce: screens with wider gamuts are capable of presenting more vivid, intense colors. Different display technologies have different gamuts, from the narrow gamut of TV sets to the wide gamut of cinema and the ultra-wide gamut of laser projectors. Gamut mapping is the process of adapting the colors of an image to the gamut of the display where it is shown, and it is an essential process at every step of the imaging chain: cameras perform automatic gamut reduction, in movie postproduction colorists perform gamut mapping manually, and emerging display technologies perform automatic gamut extension. There is a trade-off between speed and quality, and no method, be it automatic or manual, is exempt from issues. One of the research outcomes of the applicant’s ERC Starting Grant IP4EC is a vision-based gamut mapping method that is automatic, of extremely low computational complexity, and produces images and videos that look natural, without any halos, spurious colors or artifacts. The model has been validated confirming that it outperforms state of the art algorithms in terms of users’ preference. A European patent application has been filed. The core idea for this Proof of Concept proposal is to make a series of products that highlight the capabilities of our gamut mapping method on three distinct scenarios: image and video capture, professional post-production of photography and cinema, and image and video display. Specifically, this project will produce, in a B2C commercial approach, a free web application and commercial mobile apps for iOS and Android systems intended for the general public, plus commercial plug-ins for professional movie and photo post-production software. We will formulate a business plan around these products, that also show the potential of our model for other applications for which we intend to license our technology and provide services, in a B2B commercial approach.
Champ scientifique
- natural sciencescomputer and information sciencessoftware
- engineering and technologymaterials engineeringcolors
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsensorsoptical sensors
- natural sciencescomputer and information sciencesartificial intelligencecomputer vision
- humanitiesartsmodern and contemporary artcinematography
Programme(s)
Régime de financement
ERC-POC - Proof of Concept GrantInstitution d’accueil
08002 Barcelona
Espagne